README.md

---

language:

• rm-vallader license: apache-2.0 tags:
• automatic-speech-recognition
• mozilla-foundation/common_voice_8_0
• generated_from_trainer
• rm-vallader
• robust-speech-event
• model_for_talk datasets:
• common_voice model-index:
• name: XLS-R-300M - Tatar results:
  • task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: Common Voice 7 type: mozilla-foundation/common_voice_8_0 args: rm-vallader metrics:
    • name: Test WER type: wer value: 0.26472007722007723
    • name: Test CER type: cer value: 0.05860608074430969

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - RM-VALLADER dataset. It achieves the following results on the evaluation set:

• Loss: 0.2754
• Wer: 0.2831

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 7.5e-05
• train_batch_size: 32
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 100.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.927	15.15	500	2.9196	1.0
1.3835	30.3	1000	0.5879	0.5866
0.7415	45.45	1500	0.3077	0.3316
0.5575	60.61	2000	0.2735	0.2954
0.4581	75.76	2500	0.2707	0.2802
0.3977	90.91	3000	0.2785	0.2809

Framework versions

• Transformers 4.17.0.dev0
• Pytorch 1.10.2+cu102
• Datasets 1.18.2.dev0
• Tokenizers 0.11.0